sws-spark-dissemination-helper 0.0.157__py3-none-any.whl → 0.0.159__py3-none-any.whl

sws_spark_dissemination_helper/SWSBronzeIcebergSparkHelper.py

@@ -687,7 +687,7 @@ class SWSBronzeIcebergSparkHelper:
         else:
             self.disseminated_tag_df = self.df_bronze
 
-        if not from_tag and len(dimensions) != 0:
+        if not from_tag and dimensions is not None and len(dimensions) != 0:
             for dimension_name, codes in dimensions.items():
                 logging.info(f"dimension_name: {dimension_name}")
                 logging.info(f"codes: {codes}")

sws_spark_dissemination_helper/SWSPostgresSparkReader.py

@@ -94,25 +94,37 @@ class SWSPostgresSparkReader:
 
             logging.info(f"{pg_table} read start")
 
-            # Read observations from the PostgreSQL table into a DataFrame
-            df = (
-                self.spark.read.format("jdbc")
-                .option("customSchema", custom_schema)
-                .option("dbtable", pg_table)
-                .option("partitionColumn", partition_column)
-                .option("lowerBound", min_id)
-                .option("upperBound", max_id)
-                .option("numPartitions", num_partitions)
-                .option("fetchsize", "1000")
-                .option("url", self.jdbc_url)
-                .option("user", self.jdbc_conn_properties["user"])
-                .option("password", self.jdbc_conn_properties["password"])
-                .option("driver", SPARK_POSTGRES_DRIVER)
-                .load()
-                # .repartition(1024, partition_column)
-                # .sortWithinPartitions(partition_column)
-                # .cache()
-            )
+            if min_id is None or max_id is None:
+                df = (
+                    self.spark.read.format("jdbc")
+                    .option("customSchema", custom_schema)
+                    .option("dbtable", pg_table)
+                    .option("fetchsize", "1000")
+                    .option("url", self.jdbc_url)
+                    .option("user", self.jdbc_conn_properties["user"])
+                    .option("password", self.jdbc_conn_properties["password"])
+                    .option("driver", SPARK_POSTGRES_DRIVER)
+                    .load()
+                )
+            else:
+                df = (
+                    self.spark.read.format("jdbc")
+                    .option("customSchema", custom_schema)
+                    .option("dbtable", pg_table)
+                    .option("partitionColumn", partition_column)
+                    .option("lowerBound", min_id)
+                    .option("upperBound", max_id)
+                    .option("numPartitions", num_partitions)
+                    .option("fetchsize", "1000")
+                    .option("url", self.jdbc_url)
+                    .option("user", self.jdbc_conn_properties["user"])
+                    .option("password", self.jdbc_conn_properties["password"])
+                    .option("driver", SPARK_POSTGRES_DRIVER)
+                    .load()
+                    # .repartition(1024, partition_column)
+                    # .sortWithinPartitions(partition_column)
+                    # .cache()
+                )
         else:
             df = (
                 self.spark.read.format("jdbc")

{sws_spark_dissemination_helper-0.0.157.dist-info → sws_spark_dissemination_helper-0.0.159.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sws-spark-dissemination-helper
-Version: 0.0.157
+Version: 0.0.159
 Summary: A Python helper package providing streamlined Spark functions for efficient data dissemination processes
 Project-URL: Repository, https://github.com/un-fao/fao-sws-it-python-spark-dissemination-helper
 Author-email: Daniele Mansillo <danielemansillo@gmail.com>

{sws_spark_dissemination_helper-0.0.157.dist-info → sws_spark_dissemination_helper-0.0.159.dist-info}/RECORD

@@ -1,13 +1,13 @@
-sws_spark_dissemination_helper/SWSBronzeIcebergSparkHelper.py,sha256=rgel_CLWb-BbS5VF59ESlX5-KP9nxCkEe2ewHyGzEpw,28841
+sws_spark_dissemination_helper/SWSBronzeIcebergSparkHelper.py,sha256=ocuau0WtpyRwui0qwdQ_Rxh4nYPOyZoHpGKaWRa6B3Q,28868
 sws_spark_dissemination_helper/SWSDatatablesExportHelper.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 sws_spark_dissemination_helper/SWSEasyIcebergSparkHelper.py,sha256=u1fFUagXvVPJirSIesuXrCbFMuZ2jQnbz1yjk1MqRwg,25061
 sws_spark_dissemination_helper/SWSGoldIcebergSparkHelper.py,sha256=KZy6v4V3ugzKq_0L8JLmTPClN0hx-9uWpAwNFcs37Og,19339
-sws_spark_dissemination_helper/SWSPostgresSparkReader.py,sha256=RFAAJx3F9I6l3JJ4xHFN4rZuNeVN9asMvP6oO0QDBlI,17851
+sws_spark_dissemination_helper/SWSPostgresSparkReader.py,sha256=KpG8gp8Ai9pHDiKhUOTcXWxxmFGeKEE3XKlI_Y-SveU,18453
 sws_spark_dissemination_helper/SWSSilverIcebergSparkHelper.py,sha256=qioLv3SlJEfk0LzTiwfXRtZXVImPOJUeh9k1XwHC-pA,26225
 sws_spark_dissemination_helper/__init__.py,sha256=42TPbk7KxAud_qY3Sr_F4F7VjyofUlxEJkUXAFQsjRo,327
 sws_spark_dissemination_helper/constants.py,sha256=_VZXdX5ARnlNzqQEJoFqY_g5r5KyF3cez7SZKV6bYrs,12915
 sws_spark_dissemination_helper/utils.py,sha256=G7lQqNRrvqZpgm9WmddD7fWsI8IVn09x1p3cV3458EA,21963
-sws_spark_dissemination_helper-0.0.157.dist-info/METADATA,sha256=4gQ4DieSt5X3K9cvEF7tZNuYEJuQQLJ9ZDNqOcOJJCY,2824
-sws_spark_dissemination_helper-0.0.157.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-sws_spark_dissemination_helper-0.0.157.dist-info/licenses/LICENSE,sha256=zFzeb_j_6pXEHwH8Z0OpIkKFJk7vmhZjdem-K0d4zU4,1073
-sws_spark_dissemination_helper-0.0.157.dist-info/RECORD,,
+sws_spark_dissemination_helper-0.0.159.dist-info/METADATA,sha256=JMSC-t_4LKJZNufyFNAe9rShRBSlQUHge-06z4slJ4c,2824
+sws_spark_dissemination_helper-0.0.159.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+sws_spark_dissemination_helper-0.0.159.dist-info/licenses/LICENSE,sha256=zFzeb_j_6pXEHwH8Z0OpIkKFJk7vmhZjdem-K0d4zU4,1073
+sws_spark_dissemination_helper-0.0.159.dist-info/RECORD,,